TALoS: A Test-Time Adaptation Approach for Enhancing Semantic Scene Completion Using LiDAR Data
TALoS, a novel test-time adaptation method, leverages the sequential nature of LiDAR data in autonomous driving to improve the accuracy of semantic scene completion by using past and future observations as self-supervision for adapting a pre-trained model to unseen driving environments.
Context and Geometry Aware Voxel Transformer for Semantic Scene Completion
This paper introduces CGFormer, a novel neural network architecture for semantic scene completion that leverages context-aware query generation and 3D deformable cross-attention within a voxel transformer framework to improve the accuracy of 3D scene reconstruction from 2D images.
Camera-based 3D Semantic Scene Completion with Sparse Guidance Network
A one-stage camera-based semantic scene completion framework that propagates semantics from semantic-aware seed voxels to the whole scene based on spatial geometry cues.
Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models
A novel approach for jointly estimating missing geometry and semantics from sparse LiDAR point clouds using denoising diffusion probabilistic models.
Bridging Stereo Geometry and Bird's-Eye-View Representation for Reliable Semantic Scene Completion
The proposed BRGScene framework effectively bridges stereo geometry and bird's-eye-view (BEV) representation to achieve reliable and accurate semantic scene completion solely from stereo RGB images.
Hardness-Aware Semantic Scene Completion with Self-Distillation: Improving Accuracy in Challenging Regions
The core message of this paper is to propose a hardness-aware semantic scene completion (HASSC) approach that can effectively improve the accuracy of existing models in challenging regions without incurring extra inference cost. The key innovations are the hard voxel mining (HVM) head that leverages both global and local hardness to focus on hard voxels, and the self-distillation training strategy that enhances the stability and consistency of the model.
SLCF-Net: Semantic Scene Completion with LiDAR-Camera Fusion
SLCF-Net introduces a novel approach for Semantic Scene Completion by fusing LiDAR and camera data, achieving superior performance in SSC metrics.
SLCF-Net: Semantic Scene Completion with LiDAR-Camera Fusion
SLCF-Net introduces a novel approach for Semantic Scene Completion by fusing LiDAR and camera data to estimate missing geometry and semantics in urban driving scenarios.
Unleashing Network Potentials for Semantic Scene Completion: AMMNet Framework
The author proposes the Adversarial Modality Modulation Network (AMMNet) to address ineffective feature learning and overfitting in semantic scene completion, achieving significant performance improvements.